import numpy as np
import pandas as pd
data=pd.read_csv("Unemp.csv") #reading csv file
data
| Region | Date | Frequency | Estimated Unemployment Rate (%) | Estimated Employed | Estimated Labour Participation Rate (%) | Region.1 | longitude | latitude | |
|---|---|---|---|---|---|---|---|---|---|
| 0 | Andhra Pradesh | 31-01-2020 | M | 5.48 | 16635535 | 41.02 | South | 15.9129 | 79.740 |
| 1 | Andhra Pradesh | 29-02-2020 | M | 5.83 | 16545652 | 40.90 | South | 15.9129 | 79.740 |
| 2 | Andhra Pradesh | 31-03-2020 | M | 5.79 | 15881197 | 39.18 | South | 15.9129 | 79.740 |
| 3 | Andhra Pradesh | 30-04-2020 | M | 20.51 | 11336911 | 33.10 | South | 15.9129 | 79.740 |
| 4 | Andhra Pradesh | 31-05-2020 | M | 17.43 | 12988845 | 36.46 | South | 15.9129 | 79.740 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 262 | West Bengal | 30-06-2020 | M | 7.29 | 30726310 | 40.39 | East | 22.9868 | 87.855 |
| 263 | West Bengal | 31-07-2020 | M | 6.83 | 35372506 | 46.17 | East | 22.9868 | 87.855 |
| 264 | West Bengal | 31-08-2020 | M | 14.87 | 33298644 | 47.48 | East | 22.9868 | 87.855 |
| 265 | West Bengal | 30-09-2020 | M | 9.35 | 35707239 | 47.73 | East | 22.9868 | 87.855 |
| 266 | West Bengal | 31-10-2020 | M | 9.98 | 33962549 | 45.63 | East | 22.9868 | 87.855 |
267 rows × 9 columns
data.head(10)
| Region | Date | Frequency | Estimated Unemployment Rate (%) | Estimated Employed | Estimated Labour Participation Rate (%) | Region.1 | longitude | latitude | |
|---|---|---|---|---|---|---|---|---|---|
| 0 | Andhra Pradesh | 31-01-2020 | M | 5.48 | 16635535 | 41.02 | South | 15.9129 | 79.74 |
| 1 | Andhra Pradesh | 29-02-2020 | M | 5.83 | 16545652 | 40.90 | South | 15.9129 | 79.74 |
| 2 | Andhra Pradesh | 31-03-2020 | M | 5.79 | 15881197 | 39.18 | South | 15.9129 | 79.74 |
| 3 | Andhra Pradesh | 30-04-2020 | M | 20.51 | 11336911 | 33.10 | South | 15.9129 | 79.74 |
| 4 | Andhra Pradesh | 31-05-2020 | M | 17.43 | 12988845 | 36.46 | South | 15.9129 | 79.74 |
| 5 | Andhra Pradesh | 30-06-2020 | M | 3.31 | 19805400 | 47.41 | South | 15.9129 | 79.74 |
| 6 | Andhra Pradesh | 31-07-2020 | M | 8.34 | 15431615 | 38.91 | South | 15.9129 | 79.74 |
| 7 | Andhra Pradesh | 31-08-2020 | M | 6.96 | 15251776 | 37.83 | South | 15.9129 | 79.74 |
| 8 | Andhra Pradesh | 30-09-2020 | M | 6.40 | 15220312 | 37.47 | South | 15.9129 | 79.74 |
| 9 | Andhra Pradesh | 31-10-2020 | M | 6.59 | 15157557 | 37.34 | South | 15.9129 | 79.74 |
data.tail(10)
| Region | Date | Frequency | Estimated Unemployment Rate (%) | Estimated Employed | Estimated Labour Participation Rate (%) | Region.1 | longitude | latitude | |
|---|---|---|---|---|---|---|---|---|---|
| 257 | West Bengal | 31-01-2020 | M | 6.94 | 35820789 | 47.35 | East | 22.9868 | 87.855 |
| 258 | West Bengal | 29-02-2020 | M | 4.92 | 36964178 | 47.74 | East | 22.9868 | 87.855 |
| 259 | West Bengal | 31-03-2020 | M | 6.92 | 35903917 | 47.27 | East | 22.9868 | 87.855 |
| 260 | West Bengal | 30-04-2020 | M | 17.41 | 26938836 | 39.90 | East | 22.9868 | 87.855 |
| 261 | West Bengal | 31-05-2020 | M | 17.41 | 28356675 | 41.92 | East | 22.9868 | 87.855 |
| 262 | West Bengal | 30-06-2020 | M | 7.29 | 30726310 | 40.39 | East | 22.9868 | 87.855 |
| 263 | West Bengal | 31-07-2020 | M | 6.83 | 35372506 | 46.17 | East | 22.9868 | 87.855 |
| 264 | West Bengal | 31-08-2020 | M | 14.87 | 33298644 | 47.48 | East | 22.9868 | 87.855 |
| 265 | West Bengal | 30-09-2020 | M | 9.35 | 35707239 | 47.73 | East | 22.9868 | 87.855 |
| 266 | West Bengal | 31-10-2020 | M | 9.98 | 33962549 | 45.63 | East | 22.9868 | 87.855 |
data.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 267 entries, 0 to 266 Data columns (total 9 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Region 267 non-null object 1 Date 267 non-null object 2 Frequency 267 non-null object 3 Estimated Unemployment Rate (%) 267 non-null float64 4 Estimated Employed 267 non-null int64 5 Estimated Labour Participation Rate (%) 267 non-null float64 6 Region.1 267 non-null object 7 longitude 267 non-null float64 8 latitude 267 non-null float64 dtypes: float64(4), int64(1), object(4) memory usage: 18.9+ KB
data.describe()
| Estimated Unemployment Rate (%) | Estimated Employed | Estimated Labour Participation Rate (%) | longitude | latitude | |
|---|---|---|---|---|---|
| count | 267.000000 | 2.670000e+02 | 267.000000 | 267.000000 | 267.000000 |
| mean | 12.236929 | 1.396211e+07 | 41.681573 | 22.826048 | 80.532425 |
| std | 10.803283 | 1.336632e+07 | 7.845419 | 6.270731 | 5.831738 |
| min | 0.500000 | 1.175420e+05 | 16.770000 | 10.850500 | 71.192400 |
| 25% | 4.845000 | 2.838930e+06 | 37.265000 | 18.112400 | 76.085600 |
| 50% | 9.650000 | 9.732417e+06 | 40.390000 | 23.610200 | 79.019300 |
| 75% | 16.755000 | 2.187869e+07 | 44.055000 | 27.278400 | 85.279900 |
| max | 75.850000 | 5.943376e+07 | 69.690000 | 33.778200 | 92.937600 |
data.shape
(267, 9)
x=data['Region']
x
0 Andhra Pradesh
1 Andhra Pradesh
2 Andhra Pradesh
3 Andhra Pradesh
4 Andhra Pradesh
...
262 West Bengal
263 West Bengal
264 West Bengal
265 West Bengal
266 West Bengal
Name: Region, Length: 267, dtype: object
y=data[' Estimated Unemployment Rate (%)']
y
0 5.48
1 5.83
2 5.79
3 20.51
4 17.43
...
262 7.29
263 6.83
264 14.87
265 9.35
266 9.98
Name: Estimated Unemployment Rate (%), Length: 267, dtype: float64
df2=data.iloc[:,3]
df2
0 5.48
1 5.83
2 5.79
3 20.51
4 17.43
...
262 7.29
263 6.83
264 14.87
265 9.35
266 9.98
Name: Estimated Unemployment Rate (%), Length: 267, dtype: float64
import plotly.express as px
import matplotlib.pyplot as plt
fg=px.bar(data,x='Region',y=' Estimated Unemployment Rate (%)',color='Region',title='unemployment rate statewise by bargraph',template='plotly')
fg.update_layout(xaxis={'categoryorder':'total descending'})
fg.show()
fg=px.bar(data,x='Region.1',y=' Estimated Unemployment Rate (%)',color='Region',title='unemployment rate statewise by bargraph',template='plotly')
fg.update_layout(xaxis={'categoryorder':'total descending'})
fg.show()
fg=px.box(data,x='Region',y=' Estimated Unemployment Rate (%)',color='Region',title='unemployment rate statewise by boxplotgraph',template='plotly')
fg.update_layout(xaxis={'categoryorder':'total descending'})
fg.show()
fg=px.scatter(data,x='Region',y=' Estimated Unemployment Rate (%)',color='Region',title='unemployment rate statewise by scattergraph',template='plotly')
fg.update_layout(xaxis={'categoryorder':'total descending'})
fg.show()
fg=px.histogram(data,x='Region',y=' Estimated Unemployment Rate (%)',color='Region',title='unemployment rate state wise by histogram',template='plotly')
fg.update_layout(xaxis={'categoryorder':'total descending'})
fg.show()